Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4397 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.7186. Min Act: -0.0000

Data Index: 846415 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6716. Min Act: -0.0000

Data Index: 48586 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6598. Min Act: -0.0000

Data Index: 204871 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1282911 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1290426 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1349698 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1112352 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5992. Min Act: -0.0000

Data Index: 6530 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5673. Min Act: -0.0000

Data Index: 70761 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5641. Min Act: -0.0000

Data Index: 712918 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5593. Min Act: -0.0000

Data Index: 446528 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5794. Min Act: -0.0000

Data Index: 910914 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5389. Min Act: 0.0000

Data Index: 1250592 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1164853 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5328. Min Act: -0.0000

Data Index: 466387 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5015. Min Act: 0.0000

Data Index: 1302786 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5052. Min Act: -0.0000

Data Index: 713257 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4881. Min Act: -0.0000

Data Index: 940021 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4848. Min Act: -0.0000

Data Index: 763428 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4905. Min Act: -0.0000

Data Index: 226278 (C4 (Web Text))

Max Activating Token Index: 819